avcodec/h264: sse2 and avx 4:2:2 idct add8 10-bit functions

Yorkfield:
 - sse2:
   - complex: 4.13x faster (1514 vs. 367 cycles)
   - simple:  4.38x faster (1836 vs. 419 cycles)

Skylake:
 - sse2:
   - complex: 3.61x faster ( 936 vs. 260 cycles)
   - simple:  3.97x faster (1126 vs. 284 cycles)
 - avx (versus sse2):
   - complex: 1.07x faster (260 vs. 244 cycles)
   - simple:  1.03x faster (284 vs. 274 cycles)

1 files changed, 11 insertions, 2 deletions

diff --git a/libavcodec/x86/h264dsp_init.c b/libavcodec/x86/h264dsp_init.c
index ed52c4d8ef..c6c643aa8a 100644
--- a/libavcodec/x86/h264dsp_init.c
+++ b/libavcodec/x86/h264dsp_init.c
@@ -80,6 +80,9 @@ IDCT_ADD_REP_FUNC2(, 8, 10, avx)
 
 IDCT_ADD_REP_FUNC2(, 8_422, 8, mmx)
 
+IDCT_ADD_REP_FUNC2(, 8_422, 10, sse2)
+IDCT_ADD_REP_FUNC2(, 8_422, 10, avx)
+
 void ff_h264_luma_dc_dequant_idct_mmx(int16_t *output, int16_t *input, int qmul);
 void ff_h264_luma_dc_dequant_idct_sse2(int16_t *output, int16_t *input, int qmul);
 
@@ -319,8 +322,11 @@ av_cold void ff_h264dsp_init_x86(H264DSPContext *c, const int bit_depth,
             c->h264_idct8_dc_add = ff_h264_idct8_dc_add_10_sse2;
 
             c->h264_idct_add16 = ff_h264_idct_add16_10_sse2;
-            if (chroma_format_idc <= 1)
+            if (chroma_format_idc <= 1) {
                 c->h264_idct_add8 = ff_h264_idct_add8_10_sse2;
+            } else {
+                c->h264_idct_add8 = ff_h264_idct_add8_422_10_sse2;
+            }
             c->h264_idct_add16intra = ff_h264_idct_add16intra_10_sse2;
 #if HAVE_ALIGNED_STACK
             c->h264_idct8_add  = ff_h264_idct8_add_10_sse2;
@@ -359,8 +365,11 @@ av_cold void ff_h264dsp_init_x86(H264DSPContext *c, const int bit_depth,
             c->h264_idct8_dc_add = ff_h264_idct8_dc_add_10_avx;
 
             c->h264_idct_add16 = ff_h264_idct_add16_10_avx;
-            if (chroma_format_idc <= 1)
+            if (chroma_format_idc <= 1) {
                 c->h264_idct_add8 = ff_h264_idct_add8_10_avx;
+            } else {
+                c->h264_idct_add8 = ff_h264_idct_add8_422_10_avx;
+            }
             c->h264_idct_add16intra = ff_h264_idct_add16intra_10_avx;
 #if HAVE_ALIGNED_STACK
             c->h264_idct8_add  = ff_h264_idct8_add_10_avx;